TI

TinyKAI 3B beta

TinykaiGGUF by afridevaUpdated 2023-11-10
Download on Hugging Face
Parameters3.43B
Context2K
Layers26
Architecturellama
Smallest quant2.1 GB
Quick answer

TinyKAI 3B beta needs about 5.8 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 6 quants, from 2.1 GB (Q2_K) to 3.6 GB (Q8_0).

TinyKAI 3B beta is a 3.43B-parameter Tinykai model in GGUF format, quantized by afrideva. Its trained context length is 2K tokens. The repository has 6 quant files, from 2.1 GB (Q2_K) to 3.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.1 GB 3.3 GB
Fits Get file →
Q3_K_M2.3 GB 3.5 GB
Fits Get file →
Q4_K_M2.6 GB 3.8 GB
Fits Get file →
Q5_K_M2.8 GB 3.9 GB
Fits Get file →
Q6_K3.6 GB 4.8 GB
Fits Get file →
Q8_03.6 GB 4.8 GB
Fits Get file →

What GPU do you need for TinyKAI 3B beta?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q5_K_M (2.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 6.9 GB in use).

Which TinyKAI 3B beta quant should you choose?

Q4_K_M is the usual starting point for TinyKAI 3B beta: it balances file size and quality well. Here it is a 2.6 GB file.

The Q8_0 file is 3.6 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 2.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.43B
Layers26
Trained context2,048 tokens
KV cache (fp16)325 KB per token

Source

Quantized byafrideva
FamilyTinykai
Licenseapache-2.0
Downloads (HF)319
Last updated2023-11-10

Frequently asked questions about TinyKAI 3B beta

How much VRAM does TinyKAI 3B beta need?

About 5.8 GB at Q4_K_M with an 8K context window. That is the 2.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run TinyKAI 3B beta on an 8 GB GPU?

Yes, with Q6_K: the 3.6 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyKAI 3B beta GGUF?

It depends on the quant: Q2_K is 2.1 GB, Q3_K_M is 2.3 GB, Q4_K_M is 2.6 GB, Q5_K_M is 2.8 GB, Q6_K is 3.6 GB, Q8_0 is 3.6 GB.

What context length does TinyKAI 3B beta support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download TinyKAI 3B beta GGUF?

The files are on Hugging Face in the afrideva/TinyKAI-3B-beta-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does TinyKAI 3B beta use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from afrideva

All by afrideva →

More Tinykai models

All Tinykai →

Other tiny models

All tiny models →